tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 12:35:16 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : cont

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-01-13 14:56:52 +02:00
parent f78b396ee7
commit e4550fbafc
19 changed files with 128 additions and 79 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/speculative-simple/speculative-simple.cpp
View File

@ -45,6 +45,8 @@ int main(int argc, char ** argv) {
model_tgt = llama_init_tgt.model.get();
ctx_tgt = llama_init_tgt.context.get();
llama_kv_cache * kv = llama_get_kv_cache(ctx_tgt);
const llama_vocab * vocab = llama_model_get_vocab(model_tgt);
// load the draft model
@ -217,7 +219,7 @@ int main(int argc, char ** argv) {
{
LOG_DBG("clear kv cache from any extra tokens, n_past = %d\n", n_past);
llama_kv_cache_seq_rm(ctx_tgt, 0, n_past, -1);
llama_kv_cache_seq_rm(kv, 0, n_past, -1);
}
if ((params.n_predict >= 0 && n_predict > params.n_predict) || has_eos) {